Natural Methods for Learning and Generalization in Human-Robot Domains
作者： Monica N. Nicolescu
DOI:
关键词:
摘要: Human-robot interaction is a growing research domain; there are many approaches to robot design, depending on the particular aspects of being focused on. The challenge we address in this paper build robots that have ability learn perform complex tasks and refine their acquired capabilitie st hrough with humans environment. We propose an approach for teaching by demonstration similar one people use among themselves: demonstrate task, then allow learner it unde rt he teacher’s supervision. Depending quality learned teacher may either task again or provide specific feedback during learner’s practice trial. Thus,generalization over several demonstrations using execution trials key capabilities refining previously representations. validated these concepts Pioneer 2DX mobile learning various from demonstration.
参考文章(11)
Chrystopher L Nehaniv, Kerstin Dautenhahn, Kerstin Dautenhahn, Imitation in Animals and Artifacts ,(2002)
P. Garcia, E. Vidal, Inference of k-testable languages in the strict sense and application to syntactic pattern recognition IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 12, pp. 920- 925 ,(1990) , 10.1109/34.57687
Pedro Garcia, Enrique Vidal, Francisco Casacuberta, Local Languages, the Succesor Method, and a Step Towards a General Methodology for the Inference of Regular Grammars IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-9, pp. 841- 845 ,(1987) , 10.1109/TPAMI.1987.4767991
M.N. Nicolescu, M.J. Mataric, Experience-based representation construction: learning from human and robot teachers intelligent robots and systems. ,vol. 2, pp. 740- 745 ,(2001) , 10.1109/IROS.2001.976257
Monica N. Nicolescu, Maja J. Matarić, A hierarchical architecture for behavior-based robots Proceedings of the first international joint conference on Autonomous agents and multiagent systems part 1 - AAMAS '02. pp. 227- 233 ,(2002) , 10.1145/544741.544798
Y. Kuniyoshi, M. Inaba, H. Inoue, Learning by watching: extracting reusable task knowledge from visual observation of human performance international conference on robotics and automation. ,vol. 10, pp. 799- 822 ,(1994) , 10.1109/70.338535
Michael Kaiser, Transfer of elementary skills via human-robot interaction Adaptive Behavior. ,vol. 5, pp. 249- 280 ,(1997) , 10.1177/105971239700500303
Stefan Schaal, Learning from Demonstration neural information processing systems. ,vol. 9, pp. 1040- 1046 ,(1996)
Barry Brian Werger, Ayllu: Distributed Port-Arbitrated Behavior-Based Control Springer, Tokyo. pp. 25- 34 ,(2000) , 10.1007/978-4-431-67919-6_3
John Demiris, Gillian M. Hayes, Imitation as a dual-route process featuring predictive and learning components: a biologically plausible computational model Imitation in animals and artifacts. pp. 327- 361 ,(2002)